ALL-teach_sys/frontend_化工/simplify_content.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import re
from datetime import datetime

def create_backup(file_path):
    """创建备份文件"""
    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
    backup_path = f"{file_path}.backup_{timestamp}"
    with open(file_path, 'r', encoding='utf-8') as f:
        content = f.read()
    with open(backup_path, 'w', encoding='utf-8') as f:
        f.write(content)
    print(f"已创建备份: {backup_path}")
    return backup_path

def simplify_content_structure():
    """将content对象简化为只包含原始内容"""
    file_path = 'src/mocks/resumeInterviewMock.js'
    
    # 创建备份
    create_backup(file_path)
    
    # 有真实修改版的岗位列表（这些要保留original和modified）
    real_modified_positions = {
        "会展策划师",
        "会展执行助理",
        "会展讲解员",
        "活动策划师",
        "活动执行",
        "漫展策划师",
        "旅游规划师",
        "旅游计调专员",
        "景区运营专员",
        "文旅运营总监助理"
    }
    
    # 读取文件内容
    with open(file_path, 'r', encoding='utf-8') as f:
        content = f.read()
    
    # 处理模式：
    # 1. 找到position: "岗位名"
    # 2. 找到其后的content: {
    # 3. 如果岗位不在real_modified_positions中，将content: { original: `...`, modified: `...` } 改为 content: `...`
    
    def process_position_block(match):
        full_match = match.group(0)
        position_name = match.group(1)
        
        if position_name in real_modified_positions:
            # 保留原样
            print(f"✓ 保留 {position_name} 的original和modified结构")
            return full_match
        
        # 提取original内容
        original_match = re.search(r'original:\s*`([^`]*)`', full_match, re.DOTALL)
        if original_match:
            original_content = original_match.group(1)
            # 替换整个content对象为简单字符串
            new_content = re.sub(
                r'content:\s*\{[^}]*original:\s*`[^`]*`[^}]*modified:\s*`[^`]*`[^}]*\}',
                f'content: `{original_content}`',
                full_match,
                flags=re.DOTALL
            )
            print(f"✗ 简化 {position_name} 的content结构（删除modified）")
            return new_content
        
        return full_match
    
    # 匹配position到整个content对象的模式
    pattern = r'position:\s*"([^"]+)"[^{]*content:\s*\{[^}]*original:\s*`[^`]*`[^}]*modified:\s*`[^`]*`[^}]*\}'
    
    # 执行替换
    new_content = re.sub(pattern, process_position_block, content, flags=re.DOTALL)
    
    # 保存文件
    with open(file_path, 'w', encoding='utf-8') as f:
        f.write(new_content)
    
    print("\n处理完成！")

def verify_results():
    """验证结果"""
    file_path = 'src/mocks/resumeInterviewMock.js'
    
    with open(file_path, 'r', encoding='utf-8') as f:
        content = f.read()
    
    # 统计还有modified字段的岗位
    pattern = r'position:\s*"([^"]+)"[^}]*modified:\s*`'
    matches = re.findall(pattern, content, re.DOTALL)
    
    print("\n验证结果：")
    print("=" * 50)
    print(f"还有modified字段的岗位（共{len(set(matches))}个）：")
    for position in set(matches):
        print(f"  - {position}")
    
    # 期望的列表
    expected = {
        "会展策划师",
        "会展执行助理",
        "会展讲解员",
        "活动策划师",
        "活动执行",
        "漫展策划师",
        "旅游规划师",
        "旅游计调专员",
        "景区运营专员",
        "文旅运营总监助理"
    }
    
    found = set(matches)
    
    if found == expected:
        print("\n✓ 完美！所有岗位的modified字段都正确")
    else:
        missing = expected - found
        extra = found - expected
        
        if missing:
            print(f"\n⚠️ 缺少modified的岗位：{missing}")
        if extra:
            print(f"\n⚠️ 不应该有modified的岗位：{extra}")

def main():
    print("开始简化content结构...")
    print("=" * 50)
    
    # 简化content结构
    simplify_content_structure()
    
    # 验证结果
    verify_results()

if __name__ == "__main__":
    main()